A new study suggests online symptom trackers might not properly diagnose medical conditions. 

By Brigitt Earley
Updated July 09, 2015
Yunhee Kim

It's a familiar scenario: You experience a symptom and, not sure what it means, you turn to the Internet for a diagnosis. Suddenly, a case of bloating could be gastroenteritis—or ovarian cancer.

Now a new study from Harvard Medical School suggest online symptom trackers—tools that ask you to enter information about your ailments and then return a range of diagnoses—might not be all that accurate.

Most of these tools ask users to select symptoms from a pre-populated list of options and then return a range of potential illnesses that may cause the symptoms indicated. Many of the tools also provide advice about whether or not the user should seek immediate treatment.

In the first study to verify their accuracy, researchers created a standardized list of symptoms based on 45 clinical scenarios that are routinely used to teach and test medical students and then used 23 different online symptom checkers to input the symptoms associated with each case. One third of the tools listed the correct diagnosis as the first option for patients and half of the sites tested had the right diagnosis among the top three results. Nearly 60 percent listed the condition within their top 20 suggestions.

Though online programs may fail to produce the correct diagnosis, researchers say they are roughly equivalent to the hotlines commonly used at primary care practices and are generally better than turning to a search engine for medical advice.

"These tools may be useful in patients who are trying to decide whether they should get to a doctor quickly, but in may cases, users should be cautious and not take the information they receive from online symptom checkers as gospel," senior author Ateev Mehrotra, associate professor of health care policy and medicine at Harvard Medical School and Beth Israel Deaconess Medical Center said in a statement.

Lest you worry too much about their accuracy, though, most symptom checkers skewed overly cautious and recommended users seek care when staying home and monitoring the condition might have been a reasonable suggestion. And, in 80 percent of critical cases, the tools correctly recommended emergency care.

"It's not nearly as important for a patient with fever, headache, stiff neck and confusion to know whether they have meningitis or encephalitis," Mehrotra said, "as it is for them to know that they should get to an ER quickly."